Skip to main content

AI-driven software delivery

Agents build.Gates decide.You ship.

Buildmill runs the whole delivery loop — intent to release to observe — with AI agents doing the work and a checkpoint at every stage boundary. Deterministic floors catch what must never slip, calibrated thresholds decide what advances, and you're asked only when it matters.

Gates
Every stage boundary
Runners
Your own hardware
Autonomy
Computed, not configured
Status
Closed beta

The loop

One loop, from intent to observe.

Every piece of work rides a pipeline: product stages shape the intent, repo stages build it, and a gate sits at every boundary. Multi-repo products fan out per repo and fan back in for review. Pipelines freeze at creation — mid-flight edits never mutate work in progress.

  1. 01intentAn idea enters the mill
  2. 02triageWorth doing? Routed where?
  3. 03refineSharpened into a spec
  4. 04decomposeSplit across repos
  5. 05buildFan-out: one chain per repo
  6. 06reviewFan-in — the whole change, judged
  7. 07releaseShipped
  8. 08observeThe running product feeds back

The build stage is its own repo-level chain — test-writer → dev-planner → implement → quality → pr — each stage with its own gate, each gate overridable per repo. Observe closes the loop: deterministic scanners plus a product-composed observer watch the running product and capture confirmed findings back onto its backlog.

Gates

A checkpoint at every stage boundary.

A gate is a small, explicit contract: deterministic floor checks that can never be scored past, a threshold the work's score must clear, and a defined path when it doesn't. 0 never asks. always always asks. Everything between is earned.

gate := { enabled · threshold: always | 0..1 · floor[] · scorers[] · retry · rerouteTo? }

Floors are law

Deterministic checks — verify-must-run, diff ceilings, never-touch paths — that no score can override. Fail a floor and the work is auto-declined, retried within bounds, then parked.

Thresholds are calibrated

An inline verifier scores every stage. At or above the gate's threshold, work advances on its own; below it, a human sees exactly what the verifier saw.

Rework before humans

Below the bar, a numeric gate first spends one automatic rework cycle when the verifier drafted the feedback — and the redo must clear the threshold on its own score.

Declines reroute

A gate can send declined work back to an earlier stage — quality declines rework the tests, security declines rework the plan — instead of retrying the same failure.

Autonomy is computed

A product is fully autonomous exactly when no gate in its workflows can require a human. It's a fact derived from your gates, not a switch you flip.

Mission-critical templates

For products where a bad release costs real money or trust: every judgment gate is unconditional human review, hard floors make the non-negotiables deterministic, and a dedicated security-review stage judges with frontier models.

Act

One decision at a time.

When a gate needs a human, it lands in Act. The marshaler presents each developer the single optimal pending decision org-wide — product priority × stage urgency × age — claim-leased so two people never review the same item.

  • approveThe work advances
  • declineBack, with feedback
  • refineReshape the ask
  • skipNot yours — release it
  • nixKill the item

Humans decide. Agents execute.

Architecture

Your code never touches our servers.

Buildmill splits cleanly in two: a hosted control plane that orchestrates, and runners you own that execute. The boundary is structural, not policy.

Control plane

Hosted

The system of record: products, workflows, gate math, budgets, decisions. It schedules work and records outcomes — it holds no tenant git credentials, clones no repos, and executes no agent code.

  • Org-scoped tenancy on every row
  • One write path — console, CLI, and runners all mutate through the API
  • Gate math, budget governor, calibration

Your runners

Your hardware

A small daemon on machines you own. It claims work, executes stages in worktrees with your git and agent credentials, and posts results back. Multiple runners per org are free — leases keep them honest.

  • Your git creds, your agent CLI, your metal
  • Artifacts move via presigned URLs
  • The control plane never sees your code

Clients: the console at app.buildmill.io (GitHub sign-in) — CLI on the roadmap.

Closed beta

Access is gated. Of course it is.

Buildmill is in closed beta: sign-in is GitHub OAuth and org creation is invite-only while the loop hardens on real products. If you want your delivery running through gates — agents doing the work, floors holding the line, your hardware executing — tell us what you'd put through the mill.

Closed beta · sign in with GitHub · org creation by invite